commit 8034f71a8ee073d5d4f0e7012a05ebad06c97d4c Author: ModelHub XC Date: Wed Sep 23 15:23:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a4f7045 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-Llama-3.2-CoT-Summary.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-Llama-3.2-CoT-Summary.IQ4_XS.gguf b/Hermes-Llama-3.2-CoT-Summary.IQ4_XS.gguf new file mode 100644 index 0000000..92e7588 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65324458f4a9f3df8bd9fe83d86268e204e41ebbe65e7f6e53486104f44a8ba +size 1840903552 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q2_K.gguf b/Hermes-Llama-3.2-CoT-Summary.Q2_K.gguf new file mode 100644 index 0000000..78b31fa --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd907cacb7e6a58e150ff024749d3da01cbba944b5999049a9712996ce3df9e +size 1363932544 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q3_K_L.gguf b/Hermes-Llama-3.2-CoT-Summary.Q3_K_L.gguf new file mode 100644 index 0000000..70b3f53 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d11ada5c593fe2669b327991e421a4787867648407504361becff0fe73eb55 +size 1815344512 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q3_K_M.gguf b/Hermes-Llama-3.2-CoT-Summary.Q3_K_M.gguf new file mode 100644 index 0000000..04cfdd0 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa63fc6d41b66bf4b5feb1e2558481fef1e64607f9ac80ca12a1a8db41d33b3f +size 1687156096 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q3_K_S.gguf b/Hermes-Llama-3.2-CoT-Summary.Q3_K_S.gguf new file mode 100644 index 0000000..f450fa3 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485d5051119c3cfd97a21763104dec671a0885d045747237df68b82066d3ccaa +size 1542845824 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q4_K_M.gguf b/Hermes-Llama-3.2-CoT-Summary.Q4_K_M.gguf new file mode 100644 index 0000000..679e398 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:514f17eb3fdd50751368cb0d6b13d298ba4f043c055698eb6b45702c36242dd8 +size 2019374464 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q4_K_S.gguf b/Hermes-Llama-3.2-CoT-Summary.Q4_K_S.gguf new file mode 100644 index 0000000..937a761 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879fee011a908a1777134fc014fb5ebb6a6ae86819d7cb106cf401b0dbf67844 +size 1928197504 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q5_K_M.gguf b/Hermes-Llama-3.2-CoT-Summary.Q5_K_M.gguf new file mode 100644 index 0000000..4e0873e --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c548aa62555feebccfc43bead491e6891ae7f2bef31acf74154e55e2f8e66e +size 2322150784 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q5_K_S.gguf b/Hermes-Llama-3.2-CoT-Summary.Q5_K_S.gguf new file mode 100644 index 0000000..21de252 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1b2c2fe9e2826a6fea0b7d5c9d7d45d9769d1b2388bffb2484f698f37d2b6d +size 2269508992 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q6_K.gguf b/Hermes-Llama-3.2-CoT-Summary.Q6_K.gguf new file mode 100644 index 0000000..8c81cdd --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c378cc77939f64a606eaf18e6cce36b1a8bd6243d16f29d1ef2551896775d08f +size 2643850624 diff --git a/Hermes-Llama-3.2-CoT-Summary.Q8_0.gguf b/Hermes-Llama-3.2-CoT-Summary.Q8_0.gguf new file mode 100644 index 0000000..f13bb7e --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630f5cc884f1cb1784f10199b340c4aff169ba4239be0bb18c4537d413a2cfb0 +size 3421896064 diff --git a/Hermes-Llama-3.2-CoT-Summary.f16.gguf b/Hermes-Llama-3.2-CoT-Summary.f16.gguf new file mode 100644 index 0000000..e979ca3 --- /dev/null +++ b/Hermes-Llama-3.2-CoT-Summary.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5453408b430c5db29260b553d9a763473f9827c2ab786e684b077772d9303c1 +size 6433684864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a45df81 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Triangle104/Hermes-Llama-3.2-CoT-Summary +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Triangle104/Hermes-Llama-3.2-CoT-Summary + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hermes-Llama-3.2-CoT-Summary-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-Llama-3.2-CoT-Summary-GGUF/resolve/main/Hermes-Llama-3.2-CoT-Summary.f16.gguf) | f16 | 6.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +